Class of neuron for full connected layers.
More...
|
static double | alpha =0.8 |
| Multiplier to momentum in SGD optimization. More...
|
|
Class of neuron for full connected layers.
Detailed description on the link.
Definition at line 514 of file NeuroNet.mqh.
◆ CNeuron()
CNeuron::CNeuron |
( |
void |
| ) |
|
|
inline |
◆ ~CNeuron()
CNeuron::~CNeuron |
( |
void |
| ) |
|
|
inline |
◆ activationFunction()
double CNeuronBase::activationFunction |
( |
double |
x | ) |
|
|
protectedvirtualinherited |
Method to calculate activation function.
- Parameters
-
- Returns
- Result of activation function.
Reimplemented in CNeuronConv.
Definition at line 2663 of file NeuroNet.mqh.
◆ activationFunctionDerivative()
double CNeuronBase::activationFunctionDerivative |
( |
double |
x | ) |
|
|
virtualinherited |
Calculate derivative of activation function.
- Parameters
-
- Returns
- Derivative
Reimplemented in CNeuronConv.
Definition at line 2680 of file NeuroNet.mqh.
◆ calcHiddenGradients()
bool CNeuronBase::calcHiddenGradients |
( |
CObject *& |
TargetObject | ) |
|
|
virtualinherited |
Dispatch method for defining the subroutine for transfer gradient to previous layer.
- Parameters
-
TargetObject | Pointer to next layer. |
Definition at line 959 of file NeuroNet.mqh.
◆ calcOutputGradients()
bool CNeuron::calcOutputGradients |
( |
double |
targetVals | ) |
|
|
virtual |
Method of output gradients calculation.
- Parameters
-
Definition at line 590 of file NeuroNet.mqh.
◆ feedForward()
bool CNeuronBase::feedForward |
( |
CObject *& |
SourceObject | ) |
|
|
virtualinherited |
Dispatch method for defining the subroutine for Feed Forward process.
- Parameters
-
SourceObject | Pointer to previos layer. |
Definition at line 859 of file NeuroNet.mqh.
◆ getConnections()
virtual CArrayCon* CNeuronBase::getConnections |
( |
| ) |
|
|
inlinevirtualinherited |
Method to get access to array of connections.
- Returns
- Pointer to connections array
Definition at line 443 of file NeuroNet.mqh.
◆ getGradient()
virtual double CNeuronBase::getGradient |
( |
| ) |
|
|
inlinevirtualinherited |
Return gradient of neuron.
- Returns
- Gradient
Definition at line 442 of file NeuroNet.mqh.
◆ getOutputLayer()
virtual CLayer* CNeuronBase::getOutputLayer |
( |
void |
| ) |
|
|
inlineprotectedvirtualinherited |
Method for getting a pointer to the resulting neural layer. Not used in fully connected neural networks.
- Returns
- Pointer to layer.
Reimplemented in CNeuronLSTM, and CNeuronProof.
Definition at line 428 of file NeuroNet.mqh.
◆ getOutputVal()
virtual double CNeuronBase::getOutputVal |
( |
| ) |
|
|
inlinevirtualinherited |
Return result of feed forward operations.
- Returns
- Output value
Definition at line 439 of file NeuroNet.mqh.
◆ getPrevVal()
virtual double CNeuronBase::getPrevVal |
( |
| ) |
|
|
inlinevirtualinherited |
Return result of feed forward operations at previous iteration.
- Returns
- Previous output value
Definition at line 440 of file NeuroNet.mqh.
◆ Init()
bool CNeuronBase::Init |
( |
uint |
numOutputs, |
|
|
uint |
myIndex, |
|
|
ENUM_OPTIMIZATION |
optimization_type |
|
) |
| |
|
virtualinherited |
Method of initialization class.
- Parameters
-
numOutputs | Number of connections to next layer. |
myIndex | Index of neuron in layer. |
optimization_type | Optimization type (ENUM_OPTIMIZATION) |
- Returns
- Boolen result of operations.
Definition at line 488 of file NeuroNet.mqh.
◆ Load()
virtual bool CNeuronBase::Load |
( |
int const |
file_handle | ) |
|
|
inlinevirtualinherited |
◆ Save()
bool CNeuronBase::Save |
( |
int const |
file_handle | ) |
|
|
virtualinherited |
◆ SetActivationFunction()
◆ setGradient()
virtual void CNeuronBase::setGradient |
( |
double |
val | ) |
|
|
inlinevirtualinherited |
◆ setOutputVal()
virtual void CNeuronBase::setOutputVal |
( |
double |
val | ) |
|
|
inlinevirtualinherited |
◆ SigmoidFunction()
virtual double CNeuronBase::SigmoidFunction |
( |
double |
x | ) |
|
|
inlineprotectedvirtualinherited |
Calculating Sigmoid \(\frac{1}{1+e^x}\).
- Parameters
-
- Returns
- Result of calculation
Definition at line 426 of file NeuroNet.mqh.
◆ SigmoidFunctionDerivative()
virtual double CNeuronBase::SigmoidFunctionDerivative |
( |
double |
x | ) |
|
|
inlinevirtualinherited |
Calculate derivative of Sigmoid function.
- Parameters
-
- Returns
- Derivative
Definition at line 445 of file NeuroNet.mqh.
◆ sumDOW()
double CNeuron::sumDOW |
( |
CLayer *& |
nextLayer | ) |
|
|
virtual |
A method for collecting gradients from the next layer.
- Parameters
-
[in] | nextLayer | Pointer to next layer |
- Returns
- Total gradient to neuron.
Definition at line 560 of file NeuroNet.mqh.
◆ TanhFunction()
virtual double CNeuronBase::TanhFunction |
( |
double |
x | ) |
|
|
inlineprotectedvirtualinherited |
Calculating \(tanh(x)\).
- Parameters
-
- Returns
- Result of calculation
Definition at line 427 of file NeuroNet.mqh.
◆ TanhFunctionDerivative()
virtual double CNeuronBase::TanhFunctionDerivative |
( |
double |
x | ) |
|
|
inlinevirtualinherited |
Calculate derivative of \(tanh(x)\).
- Parameters
-
- Returns
- Derivative
Definition at line 446 of file NeuroNet.mqh.
◆ Type()
virtual int CNeuron::Type |
( |
void |
| ) |
const |
|
inlinevirtual |
◆ updateInputWeights()
bool CNeuronBase::updateInputWeights |
( |
CObject *& |
SourceObject | ) |
|
|
virtualinherited |
Dispatch method for defining the subroutine for updating weights.
- Parameters
-
SourceObject | Pointer to previos layer. |
Definition at line 887 of file NeuroNet.mqh.
◆ activation
◆ alpha
double CNeuronBase::alpha =0.8 |
|
staticinherited |
Multiplier to momentum in SGD optimization.
Definition at line 436 of file NeuroNet.mqh.
◆ Connections
Array of connections with neurons in next layer.
Definition at line 417 of file NeuroNet.mqh.
◆ gradient
double CNeuronBase::gradient |
|
protectedinherited |
◆ m_myIndex
uint CNeuronBase::m_myIndex |
|
protectedinherited |
◆ optimization
◆ outputVal
double CNeuronBase::outputVal |
|
protectedinherited |
◆ prevVal
double CNeuronBase::prevVal |
|
protectedinherited |
The documentation for this class was generated from the following file: